© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33794
    Prev
    Next
    INDEX
    Explanations

    total loss or failure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endesk
    -0.74
     stadio
    -0.74
    Dungeon
    -0.72
     schwä
    -0.71
    Allgemeine
    -0.71
     verdade
    -0.71
    クサ
    -0.71
     متری
    -0.70
    umbing
    -0.69
     flaw
    -0.69
    POSITIVE LOGITS
     total
    2.09
    Total
    1.95
    total
    1.94
     Total
    1.91
    TOTAL
    1.54
     totaled
    1.51
     TOTAL
    1.49
     loss
    1.47
     write
    1.45
     totalled
    1.38
    Activations Density 0.025%

    No Known Activations